Skip to main content

A virtual lab of large language model agents for scientific research.

Project description

Virtual Lab

PyPI - Python Version PyPI version Downloads license

Virtual Lab

The Virtual Lab is an AI-human collaboration for science research. In the Virtual Lab, a human researcher works with a team of large language model (LLM) agents to perform scientific research. Interaction between the human researcher and the LLM agents occurs via a series of team meetings, where all the LLM agents discuss a scientific agenda posed by the human researcher, and individual meetings, where the human researcher interacts with a single LLM agent to solve a particular scientific task.

Please see our paper The Virtual Lab of AI agents designs new SARS-CoV-2 nanobodies for more details on the Virtual Lab and an application to nanobody design for SARS-CoV-2.

If you use the Virtual Lab, please cite our work as follows:

Swanson, K., Wu, W., Bulaong, N.L. et al. The Virtual Lab of AI agents designs new SARS-CoV-2 nanobodies. Nature (2025). https://doi.org/10.1038/s41586-025-09442-9

Virtual Lab for nanobody design

As a real-world demonstration, we applied the Virtual Lab to design nanobodies for one of the latest variants of SARS-CoV-2 (see nanobody_design). The Virtual Lab built a computational pipeline consisting of ESM, AlphaFold-Multimer, and Rosetta and used it to design 92 nanobodies that were experimentally validated.

Please see the notebook nanobody_design/run_nanobody_design.ipynb for an example of how to use the Virtual Lab to create agents and run team and individual meetings.

Installation

The Virtual Lab can be installed using pip or by cloning the repo and installing the required packages. Installation should only take a couple of minutes.

Optionally, first create a conda environment.

conda create -y -n virtual_lab python=3.14
conda activate virtual_lab

The Virtual Lab can be installed via pip.

pip install virtual-lab

To install the latest version of the Virtual Lab locally, clone the repo and then install the package.

git clone https://github.com/zou-group/virtual_lab.git
cd virtual_lab
pip install -e .

OpenAI API Key

The Virtual Lab currently uses GPT-5.2 from OpenAI by default. Save your OpenAI API key as the environment variable OPENAI_API_KEY. For example, add export OPENAI_API_KEY=<your_key> to your .bashrc or .bash_profile.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

virtual_lab-1.2.0.tar.gz (12.1 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

virtual_lab-1.2.0-py3-none-any.whl (16.8 kB view details)

Uploaded Python 3

File details

Details for the file virtual_lab-1.2.0.tar.gz.

File metadata

  • Download URL: virtual_lab-1.2.0.tar.gz
  • Upload date:
  • Size: 12.1 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.8

File hashes

Hashes for virtual_lab-1.2.0.tar.gz
Algorithm Hash digest
SHA256 df622d9a9e62116934e98121fe8534169863e8015451ff4a08cb3f83ae0c460a
MD5 02fdeebc5b51569bb3c3c36dda1eb6d8
BLAKE2b-256 0aabd029c749c099ba29c2c28bbfcf78c66fedfb36086714ef7e7eb586e168a5

See more details on using hashes here.

File details

Details for the file virtual_lab-1.2.0-py3-none-any.whl.

File metadata

  • Download URL: virtual_lab-1.2.0-py3-none-any.whl
  • Upload date:
  • Size: 16.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.8

File hashes

Hashes for virtual_lab-1.2.0-py3-none-any.whl
Algorithm Hash digest
SHA256 29bdf6e007d00472351d4e9436880ea4db9ce52431c2a6dee9c16017c308d7bf
MD5 6d4244b8b144e2aa782b37428b25f643
BLAKE2b-256 a596291768dbba0261b66eb6ffdf9c19075b5921c33d2c6fe0e368a19f93c86b

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page